Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


32839.pdf (4.48 MB)

ETD Abstract Container

Abstract Header

Decomposing Residential Monthly Electric Utility Bill Into HVAC Energy Use Using Machine Learning

Yakkali, Sai Santosh
http://orcid.org/0000-0002-4441-0437
http://rave.ohiolink.edu/etdc/view?acc_num=ucin155437406441298

Abstract Details

2019, MS, University of Cincinnati, Engineering and Applied Science: Civil Engineering.
About 38% of total energy consumption in the US can be attributed to residential usage, 48% of which is consumed by Heating, Ventilation and Air Conditioning (HVAC) systems. Inefficient operation of energy systems in residential sector motivates many researchers to develop an easy and affective method to educate consumers and reduce inefficient usage. A detailed energy bill is proven to motivate users to reduce energy consumption by 6-20% . Further, a system or device level energy consumption data can be used to propose energy saving practices. Information of HVAC usage alone can trigger a big saving, as about half of total consumption is HVAC. However, existing methods to disaggregate usage rely on sensors or meters at the either device or central power-level, which hinders the utilization for home owners. Alternatively, information about monthly electric utility is normally accessible for households, which may be utilized to attain HVAC energy use through data mining techniques. In this study, machine learning is used to construct a regression model to accurately estimate HVAC energy used based on monthly electricity used (from utility bill), home profiles, and monthly weather data. The main dataset used for training and testing the model is from the Pecan Street home energy use dataset.
Julian Wang, Ph.D. (Committee Chair)
Hazem Elzarka, Ph.D. (Committee Member)
Jiaqi Ma, Ph.D. (Committee Member)
69 p.
Civil Engineering
predict HVAC usage; Machine learning; building physics; polynomial regression model; degree hours; monthly utility bill

Recommended Citations

Citations

  • Yakkali, S. S. (2019). Decomposing Residential Monthly Electric Utility Bill Into HVAC Energy Use Using Machine Learning [Master's thesis, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin155437406441298

    APA Style (7th edition)

  • Yakkali, Sai Santosh. Decomposing Residential Monthly Electric Utility Bill Into HVAC Energy Use Using Machine Learning. 2019. University of Cincinnati, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ucin155437406441298.

    MLA Style (8th edition)

  • Yakkali, Sai Santosh. "Decomposing Residential Monthly Electric Utility Bill Into HVAC Energy Use Using Machine Learning." Master's thesis, University of Cincinnati, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ucin155437406441298

    Chicago Manual of Style (17th edition)

ucin155437406441298
428
© 2019, some rights reserved.Creative Commons License Decomposing Residential Monthly Electric Utility Bill Into HVAC Energy Use Using Machine Learning by Sai Santosh Yakkali is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License. Based on a work at etd.ohiolink.edu.
This open access ETD is published by University of Cincinnati and OhioLINK.